公开(公告)号：US09438516B2

公开(公告)日：2016-09-06

申请号：US13104489

申请日：2011-05-10

申请人： Kirk K. Chang ,  Gi Tae Kim ,  John Unger ,  John Sucec ,  Sunil Samtani

发明人： Kirk K. Chang ,  Gi Tae Kim ,  John Unger ,  John Sucec ,  Sunil Samtani

IPC分类号： H04J3/14 ,  H04L12/801 ,  H04L12/54 ,  H04L12/851 ,  H04L12/927 ,  H04L12/911

CPC分类号： H04L47/10 ,  H04L47/11 ,  H04L47/2408 ,  H04L47/2433 ,  H04L47/245 ,  H04L47/70 ,  H04L47/805 ,  H04L47/822

摘要： In a secure network where the network characteristics are not known, a call admission control algorithm and a preemption control algorithm based on a destination node informing the source node of the observed carried traffic are used to regulate the amount of traffic that needs to be preempted by the source. The amount of traffic that needs to be preempted is based on the carried traffic measured at the destination node. The traffic to be preempted is based on the priority of the traffic, where the lowest priority traffic is the first to be preempted until the amount of traffic preempted is sufficient to allow the remaining traffic to pass through the network without congestion.

摘要翻译： 在网络特性不知道的安全网络中，使用基于通知源节点的所观察到的携带业务的目的地节点的呼叫接纳控制算法和抢占控制算法来规范需要被抢占的业务量 来源。 需要抢占的流量大小取决于在目的地节点处测量的携带流量。 要抢占的流量是基于流量的优先级，其中优先级最低的流量是首先被抢占的流量，直到被抢占的流量足以允许剩余流量通过网络而不拥塞。

公开(公告)号：US20110211480A1

公开(公告)日：2011-09-01

申请号：US13104489

申请日：2011-05-10

申请人： Kirk Chang ,  Gi Tae Kim ,  John Unger ,  John Sucec ,  Sunil Samtani

发明人： Kirk Chang ,  Gi Tae Kim ,  John Unger ,  John Sucec ,  Sunil Samtani

IPC分类号： H04L12/26

CPC分类号： H04L47/10 ,  H04L47/11 ,  H04L47/2408 ,  H04L47/2433 ,  H04L47/245 ,  H04L47/70 ,  H04L47/805 ,  H04L47/822

摘要： In a secure network where the network characteristics are not known, a call admission control algorithm and a preemption control algorithm based on a destination node informing the source node of the observed carried traffic are used to regulate the amount of traffic that needs to be preempted by the source. The amount of traffic that needs to be preempted is based on the carried traffic measured at the destination node. The traffic to be preempted is based on the priority of the traffic, where the lowest priority traffic is the first to be preempted until the amount of traffic preempted is sufficient to allow the remaining traffic to pass through the network without congestion.

摘要翻译： 在网络特性不知道的安全网络中，使用基于通知源节点的所观察到的携带业务的目的地节点的呼叫接纳控制算法和抢占控制算法来规范需要被抢占的业务量 来源。 需要抢占的流量大小取决于在目的地节点处测量的携带流量。 要抢占的流量基于流量的优先级，其中最低优先级流量首先被抢占，直到流量抢占足以允许剩余流量通过网络而没有拥塞。

公开(公告)号：US07957276B2

公开(公告)日：2011-06-07

申请号：US11116512

申请日：2005-04-28

申请人： Kirk Chang ,  Gi Tae Kim ,  John Unger ,  John Sucec ,  Sunil Samtani

发明人： Kirk Chang ,  Gi Tae Kim ,  John Unger ,  John Sucec ,  Sunil Samtani

IPC分类号： H04J3/14

CPC分类号： H04L47/10 ,  H04L47/11 ,  H04L47/2408 ,  H04L47/2433 ,  H04L47/245 ,  H04L47/70 ,  H04L47/805 ,  H04L47/822

摘要： In a secure network where the network characteristics are not known, a call admission control algorithm and a preemption control algorithm based on a destination node informing the source node of the observed carried traffic are used to regulate the amount of traffic that needs to be preempted by the source. The amount of traffic that needs to be preempted is based on the carried traffic measured at the destination node. The traffic to be preempted is based on the priority of the traffic, where the lowest priority traffic is the first to be preempted until the amount of traffic preempted is sufficient to allow the remaining traffic to pass through the network without congestion.

摘要翻译： 在网络特性不知道的安全网络中，使用基于通知源节点的所观察到的携带业务的目的地节点的呼叫接纳控制算法和抢占控制算法来规范需要被抢占的业务量 来源。 需要抢占的流量大小取决于在目的地节点处测量的携带流量。 要抢占的流量基于流量的优先级，其中最低优先级流量首先被抢占，直到流量抢占足以允许剩余流量通过网络而没有拥塞。

公开(公告)号：US20100011118A1

公开(公告)日：2010-01-14

申请号：US11116512

申请日：2005-04-28

申请人： Kirk Chang ,  Gi Tae Kim ,  John Unger ,  John Sucec ,  Sunil Samtani

发明人： Kirk Chang ,  Gi Tae Kim ,  John Unger ,  John Sucec ,  Sunil Samtani

IPC分类号： G06F15/16

CPC分类号： H04L47/10 ,  H04L47/11 ,  H04L47/2408 ,  H04L47/2433 ,  H04L47/245 ,  H04L47/70 ,  H04L47/805 ,  H04L47/822

摘要： In a secure network where the network characteristics are not known, a call admission control algorithm and a preemption control algorithm based on a destination node informing the source node of the observed carried traffic are used to regulate the amount of traffic that needs to be preempted by the source. The amount of traffic that needs to be preempted is based on the carried traffic measured at the destination node. The traffic to be preempted is based on the priority of the traffic, where the lowest priority traffic is the first to be preempted until the amount of traffic preempted is sufficient to allow the remaining traffic to pass through the network without congestion.

摘要翻译： 在网络特性不知道的安全网络中，使用基于通知源节点的所观察到的携带业务的目的地节点的呼叫接纳控制算法和抢占控制算法来规范需要被抢占的业务量 来源。 需要抢占的流量大小取决于在目的地节点处测量的携带流量。 要抢占的流量基于流量的优先级，其中最低优先级流量首先被抢占，直到流量抢占足以允许剩余流量通过网络而没有拥塞。

公开(公告)号：US20070242616A1

公开(公告)日：2007-10-18

申请号：US11251224

申请日：2005-10-14

申请人： Kirk Chang ,  John Sucec ,  Harshad Tanna ,  John Lee ,  Sunil Samtani

发明人： Kirk Chang ,  John Sucec ,  Harshad Tanna ,  John Lee ,  Sunil Samtani

IPC分类号： H04J1/16 ,  H04L12/26

CPC分类号： H04L47/283 ,  H04L43/0858 ,  H04L43/0882 ,  H04L43/106 ,  H04L47/10 ,  H04L47/11 ,  H04L47/14 ,  H04L47/25 ,  H04L47/28

摘要： Without using additional probing packets, estimates of the narrow link bandwidth and available bandwidth of a network path are computed based on existing traffic. The network can be of different types such as a wireless battlefield network context or a wired or wireless commercial network environment. “Fast packets”, i.e. those packets which do not experience any queuing delay in the network, are identified. Fast packets are identified to resolve end-to-end packet delay into its constituent components (deterministic, transmission and queuing delays), estimate path utilization and eliminate the uncertainty (false alarms) that causes the prior art method to lose its effectiveness. An estimation algorithm computes end-to-end transmission delay and end-to-end deterministic delay of fast packets traveling along a path in a network. Examples of deterministic delay include satellite propagation delays and clock effects. Then, based on the results of the fast packet identifying algorithm, two logic branches are followed. A first branch calculates utilization and a second branch calculates narrow link bandwidth. The narrow link bandwidth is determined from the packet pair dispersion. The available bandwidth is obtained from the narrow link bandwidth and the utilization. Estimation of available bandwidth for an end-to-end network path allows traffic sources to judiciously regulate the volume of application traffic injected into the network.

摘要翻译： 在不使用附加探测分组的情况下，基于现有流量来计算网络路径的窄链路带宽和可用带宽的估计。 该网络可以是不同类型的，例如无线战场网络环境或有线或无线商业网络环境。 识别“快速分组”，即在网络中没有经历任何排队延迟的分组。 识别快速分组以将端到端分组延迟解析为其组成组件（确定性，传输和排队延迟），估计路径利用率并消除导致现有技术方法失效的不确定性（假警报）。 估计算法计算沿着网络中的路径行进的快速分组的端到端传输延迟和端到端确定性延迟。 确定性延迟的例子包括卫星传播延迟和时钟效应。 然后，基于快速分组识别算法的结果，跟随两个逻辑分支。 第一个分支计算利用率，第二个分支计算窄链路带宽。 窄链路带宽由分组对色散决定。 可用带宽从窄链路带宽和利用率获得。 估计端到端网络路径的可用带宽允许流量源明智地调节注入网络的应用流量。